Ilia Shumailov: uncertainty

Transcript context

…Mhmm. Did you see that anthropic paper? What was it called? Agenic misalignment Mhmm. Where they I mean, you you better set this up better than me, but, know, they they set up this kind of contrived scenario, and the the AI tried to blackmail someone because they said that they were having an the boss was was having an affair or something like that. The AI didn't wanna be switched off. And it's just absolutely crazy what what these things do. Yeah. I I don't know. Like, I find it very hard to extract sort of useful pieces of information out of this. Can a model do this? I'm sure it can. It's and I'm sure as the models get more sophisticated, we'll see a lot more phenomenons that we don't even think about today. Like, for example, me and you can communicate via WhatsApp and get end to end to end encryption. Right? So nobody can even, like, by looking at the traffic, tell what we're talking about. What stops me from talking to a model in in an end to end encrypted way? Right? Maybe we'll need an external tooling. Maybe we need to teach it how to do, I don't know, power calculations, but this is coming. It's like To what extent do you think you can read anything about what the model was thinking from its thinking tray?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.